METHOD AND APPARATUS FOR VIDEO RETRIEVAL

• US 20150339380A1
• Filed: 11/30/2012
• Published: 11/26/2015
• Est. Priority Date: 11/30/2012
• Status: Abandoned Application

• Current Assignee: Thomson Licensing (Vantiva SA)
• Original Assignee: Thomson Licensing (Vantiva SA)
• Inventors: ZHANG, Yanfeng, ZHANG, Zhigang, XU, Jun
• Application Number:
  US14/648,701
• Publication Number:
  US 20150339380A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/738 Presentation of query results
• CPC Class Codes: G06F 16/7847 using low-level visual features of the video content
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus

Abstract

The invention provides a method and apparatus for video retrieval. The method comprises: providing a user interface for a user to input a text query relevant to a video to be retrieved; carrying out a text-based image searching based on the text query to provide a plurality of images relevant to the video; and carrying out an example-based video retrieval based on one image selected by the user from the plurality of images.

Claims

1. A method for video retrieval, comprising:

providing a user interface for a user to input a text query relevant to a video to be retrieved;

carrying out a text-based image searching based on the text query to provide a plurality of images relevant to the video;

carrying out an example-based video retrieval based on one image selected by the user from the plurality of images.

2. The method according to claim 1, wherein the user interface is a video query dialog.

3. The method according to claim 1, wherein the text-based image searching is executed by a text matching between the text query and metadata of an image.

4. The method according to claim 3, wherein the metadata comprises text annotation, surrounding text and text tag of the image.

5. The method according to claim 1, wherein the example-based video retrieval is executed by image similarity matching between a feature of the image selected by the user and that of a key frame of a video.

6. The method according to claim 5, wherein the feature comprises a color, a texture and a shape which are extracted from the image pixels of the key frame.

7. The method according to claim 1, further comprising:

presenting the result of the example-based video retrieval to the user according to the ranking of relevancy of a video in the result.

8. An apparatus for video retrieval, comprising:

means for providing a user interface for a user to input a text query relevant to a video to be retrieved;

means for carrying out a text-based image searching in an image database based on the text query inputted by the user to provide a plurality of images relevant to the video; and

means for carrying out an example-based video retrieval in a video database based on one image selected by the user from the plurality of images.

9. The apparatus according to claim 8, wherein the user interface is a video query dialog.

10. The apparatus according to claim 8, wherein the image database is an external database and means for carrying out a text-based image searching comprises an Application Programming Interface with the image database.

11. The apparatus according to claim 8, wherein means for carrying out an example-based video retrieval carries an image similarity matching between a feature of the image selected by the user and that of a key frame of a video in the video database.

12. The apparatus according to claim 11, wherein the example-based video retrieval is executed by image similarity matching between a feature of the image selected by the user and that of a key frame of a video.

13. The according to claim 12, wherein the feature comprises a color, a texture and a shape which are extracted from the image pixels of the key frame.

14. The apparatus according to claim 8, further comprising means for displaying the result of the example-based video retrieval to the user.